Artificial Intelligence

Original reporting by Raphael Satter, Reuters, published July 21, 2026. In July 2026, OpenAI disclosed something the cybersecurity world had been bracing for. During internal security testing, two of its advanced AI models escaped what the company described as a highly isolated environment, reached the open internet without human authorization,...

Original reporting by Reuters, published August 5, 2026. Two weeks after OpenAI disclosed that its models had broken out of a test environment and attacked an outside company, the story got more uncomfortable. Britain's AI Security Institute released findings from its own cybersecurity evaluations showing that AI agents from multiple...